| Project/Area Number |
25540168
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Entertainment and game informatics 1
|
|---|
| Research Institution | Nagoya University |
|---|
Principal Investigator |
TAKEDA Kazuya 名古屋大学, 情報科学研究科, 教授 (20273295)
|
|---|
| Research Collaborator |
KAWABUCHI Shota 名古屋大学, 大学院情報科学研究科
|
|---|
| Project Period (FY) |
2013-04-01 – 2015-03-31
|
| Project Status |
Completed (Fiscal Year 2014)
|
| Budget Amount *help |
¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000)
Fiscal Year 2014: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2013: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
|
|---|
| Keywords | 主観的類似度 / 回答行列 / 感性情報 / 音楽情報処理 / 選考行列 / 多次元尺度解析 / 数量化理論 / 線形判別モデル / 音楽推薦 |
|---|
| Outline of Final Research Achievements |
We conducted data collection for individuality analysis of subjective music similarity. 27 subjects evaluated similarity for 200 pairs chosen from RWC popular music database, a widely used database in the field of music information processing. Each subject also evaluated similarity for melody, tempo/rhythm, vocals and instruments for the pairs. By analyzing collected data, it is suggested that decision boundaries between similar and dissimilar pairs vary widely between individuals. Using the collected data, we trained optimized distance function between songs (weighted Euclidean distance) for each individual. In the result, training of distance function improved similarity estimation precision for vocals. From this fact, the effect of individual optimization using weighted Euclidean distance was confirmed.
|
